Merge branches 'arm/renesas', 'arm/smmu', 'x86/amd', 'core' and 'x86/…

…vt-d' into next

Documentation/admin-guide/cgroup-v2.rst

@@ -1432,7 +1432,7 @@ PAGE_SIZE multiple when read back.
 	  sec_pagetables
 		Amount of memory allocated for secondary page tables,
 		this currently includes KVM mmu allocations on x86
-		and arm64.
+		and arm64 and IOMMU page tables.
 
 	  percpu (npn)
 		Amount of memory used for storing per-cpu kernel

Documentation/devicetree/bindings/iommu/qcom,tbu.yaml

@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/qcom,tbu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm TBU (Translation Buffer Unit)
+
+maintainers:
+  - Georgi Djakov <quic_c_gdjako@quicinc.com>
+
+description:
+  The Qualcomm SMMU500 implementation consists of TCU and TBU. The TBU contains
+  a Translation Lookaside Buffer (TLB) that caches page tables. TBUs provides
+  debug features to trace and trigger debug transactions. There are multiple TBU
+  instances with each client core.
+
+properties:
+  compatible:
+    enum:
+      - qcom,sc7280-tbu
+      - qcom,sdm845-tbu
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interconnects:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  qcom,stream-id-range:
+    description: |
+      Phandle of a SMMU device and Stream ID range (address and size) that
+      is assigned by the TBU
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      - items:
+          - description: phandle of a smmu node
+          - description: stream id base address
+          - description: stream id size
+
+required:
+  - compatible
+  - reg
+  - qcom,stream-id-range
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,gcc-sdm845.h>
+    #include <dt-bindings/interconnect/qcom,icc.h>
+    #include <dt-bindings/interconnect/qcom,sdm845.h>
+
+    tbu@150e1000 {
+        compatible = "qcom,sdm845-tbu";
+        reg = <0x150e1000 0x1000>;
+        clocks = <&gcc GCC_AGGRE_NOC_PCIE_TBU_CLK>;
+        interconnects = <&system_noc MASTER_GNOC_SNOC QCOM_ICC_TAG_ACTIVE_ONLY
+                         &config_noc SLAVE_IMEM_CFG QCOM_ICC_TAG_ACTIVE_ONLY>;
+        power-domains = <&gcc HLOS1_VOTE_AGGRE_NOC_MMU_PCIE_TBU_GDSC>;
+        qcom,stream-id-range = <&apps_smmu 0x1c00 0x400>;
+    };
+...

Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml

@@ -50,6 +50,7 @@ properties:
               - renesas,ipmmu-r8a779a0           # R-Car V3U
               - renesas,ipmmu-r8a779f0           # R-Car S4-8
               - renesas,ipmmu-r8a779g0           # R-Car V4H
+              - renesas,ipmmu-r8a779h0           # R-Car V4M
           - const: renesas,rcar-gen4-ipmmu-vmsa  # R-Car Gen4
 
   reg:

Documentation/filesystems/proc.rst

@@ -1110,8 +1110,8 @@ KernelStack
 PageTables
               Memory consumed by userspace page tables
 SecPageTables
-              Memory consumed by secondary page tables, this currently
-              currently includes KVM mmu allocations on x86 and arm64.
+              Memory consumed by secondary page tables, this currently includes
+              KVM mmu and IOMMU allocations on x86 and arm64.
 NFS_Unstable
               Always zero. Previous counted pages which had been written to
               the server, but has not been committed to stable storage.

arch/arc/mm/dma.c

@@ -90,8 +90,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 /*
  * Plug in direct dma map ops.
  */
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	/*
 	 * IOC hardware snoops all DMA traffic keeping the caches consistent

arch/arm/mm/dma-mapping-nommu.c

@@ -33,8 +33,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 	}
 }
 
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*

arch/arm/mm/dma-mapping.c

@@ -1709,11 +1709,15 @@ void arm_iommu_detach_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
-static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    bool coherent)
+static void arm_setup_iommu_dma_ops(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
+	u64 dma_base = 0, size = 1ULL << 32;
 
+	if (dev->dma_range_map) {
+		dma_base = dma_range_map_min(dev->dma_range_map);
+		size = dma_range_map_max(dev->dma_range_map) - dma_base;
+	}
 	mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
 	if (IS_ERR(mapping)) {
 		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
@@ -1744,17 +1748,15 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 
 #else
 
-static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    bool coherent)
+static void arm_setup_iommu_dma_ops(struct device *dev)
 {
 }
 
 static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	/*
 	 * Due to legacy code that sets the ->dma_coherent flag from a bus
@@ -1774,7 +1776,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		return;
 
 	if (device_iommu_mapped(dev))
-		arm_setup_iommu_dma_ops(dev, dma_base, size, coherent);
+		arm_setup_iommu_dma_ops(dev);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;

arch/arm64/Kconfig

@@ -46,7 +46,6 @@ config ARM64
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYSCALL_WRAPPER
-	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_ZONE_DMA_SET if EXPERT
 	select ARCH_HAVE_ELF_PROT

arch/arm64/mm/dma-mapping.c

@@ -7,7 +7,6 @@
 #include <linux/gfp.h>
 #include <linux/cache.h>
 #include <linux/dma-map-ops.h>
-#include <linux/iommu.h>
 #include <xen/xen.h>
 
 #include <asm/cacheflush.h>
@@ -39,15 +38,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	dcache_clean_poc(start, start + size);
 }
 
-#ifdef CONFIG_IOMMU_DMA
-void arch_teardown_dma_ops(struct device *dev)
-{
-	dev->dma_ops = NULL;
-}
-#endif
-
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	int cls = cache_line_size_of_cpu();
 
@@ -58,8 +49,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	if (device_iommu_mapped(dev))
-		iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
 
 	xen_setup_dma_ops(dev);
 }

arch/loongarch/kernel/dma.c

@@ -8,17 +8,12 @@
 void acpi_arch_dma_setup(struct device *dev)
 {
 	int ret;
-	u64 mask, end = 0;
+	u64 mask, end;
 	const struct bus_dma_region *map = NULL;
 
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
-		const struct bus_dma_region *r = map;
-
-		for (end = 0; r->size; r++) {
-			if (r->dma_start + r->size - 1 > end)
-				end = r->dma_start + r->size - 1;
-		}
+		end = dma_range_map_max(map);
 
 		mask = DMA_BIT_MASK(ilog2(end) + 1);
 		dev->bus_dma_limit = end;

arch/mips/mm/dma-noncoherent.c

@@ -137,8 +137,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 #endif
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	dev->dma_coherent = coherent;
 }

arch/riscv/mm/dma-noncoherent.c

@@ -128,8 +128,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	ALT_CMO_OP(FLUSH, flush_addr, size, riscv_cbom_block_size);
 }
 
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
 		   TAINT_CPU_OUT_OF_SPEC,

drivers/acpi/arm64/dma.c

@@ -8,7 +8,6 @@ void acpi_arch_dma_setup(struct device *dev)
 {
 	int ret;
 	u64 end, mask;
-	u64 size = 0;
 	const struct bus_dma_region *map = NULL;
 
 	/*
@@ -23,31 +22,23 @@ void acpi_arch_dma_setup(struct device *dev)
 	}
 
 	if (dev->coherent_dma_mask)
-		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+		end = dev->coherent_dma_mask;
 	else
-		size = 1ULL << 32;
+		end = (1ULL << 32) - 1;
 
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
-		const struct bus_dma_region *r = map;
-
-		for (end = 0; r->size; r++) {
-			if (r->dma_start + r->size - 1 > end)
-				end = r->dma_start + r->size - 1;
-		}
-
-		size = end + 1;
+		end = dma_range_map_max(map);
 		dev->dma_range_map = map;
 	}
 
 	if (ret == -ENODEV)
-		ret = iort_dma_get_ranges(dev, &size);
+		ret = iort_dma_get_ranges(dev, &end);
 	if (!ret) {
 		/*
 		 * Limit coherent and dma mask based on size retrieved from
 		 * firmware.
 		 */
-		end = size - 1;
 		mask = DMA_BIT_MASK(ilog2(end) + 1);
 		dev->bus_dma_limit = end;
 		dev->coherent_dma_mask = min(dev->coherent_dma_mask, mask);

drivers/acpi/arm64/iort.c

@@ -1367,7 +1367,7 @@ int iort_iommu_configure_id(struct device *dev, const u32 *input_id)
 { return -ENODEV; }
 #endif
 
-static int nc_dma_get_range(struct device *dev, u64 *size)
+static int nc_dma_get_range(struct device *dev, u64 *limit)
 {
 	struct acpi_iort_node *node;
 	struct acpi_iort_named_component *ncomp;
@@ -1384,13 +1384,13 @@ static int nc_dma_get_range(struct device *dev, u64 *size)
 		return -EINVAL;
 	}
 
-	*size = ncomp->memory_address_limit >= 64 ? U64_MAX :
-			1ULL<<ncomp->memory_address_limit;
+	*limit = ncomp->memory_address_limit >= 64 ? U64_MAX :
+			(1ULL << ncomp->memory_address_limit) - 1;
 
 	return 0;
 }
 
-static int rc_dma_get_range(struct device *dev, u64 *size)
+static int rc_dma_get_range(struct device *dev, u64 *limit)
 {
 	struct acpi_iort_node *node;
 	struct acpi_iort_root_complex *rc;
@@ -1408,25 +1408,25 @@ static int rc_dma_get_range(struct device *dev, u64 *size)
 		return -EINVAL;
 	}
 
-	*size = rc->memory_address_limit >= 64 ? U64_MAX :
-			1ULL<<rc->memory_address_limit;
+	*limit = rc->memory_address_limit >= 64 ? U64_MAX :
+			(1ULL << rc->memory_address_limit) - 1;
 
 	return 0;
 }
 
 /**
  * iort_dma_get_ranges() - Look up DMA addressing limit for the device
  * @dev: device to lookup
- * @size: DMA range size result pointer
+ * @limit: DMA limit result pointer
  *
  * Return: 0 on success, an error otherwise.
  */
-int iort_dma_get_ranges(struct device *dev, u64 *size)
+int iort_dma_get_ranges(struct device *dev, u64 *limit)
 {
 	if (dev_is_pci(dev))
-		return rc_dma_get_range(dev, size);
+		return rc_dma_get_range(dev, limit);
 	else
-		return nc_dma_get_range(dev, size);
+		return nc_dma_get_range(dev, limit);
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,

drivers/acpi/scan.c

@@ -1675,12 +1675,7 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 	if (ret == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
-	/*
-	 * Historically this routine doesn't fail driver probing due to errors
-	 * in acpi_iommu_configure_id()
-	 */
-
-	arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT);
+	arch_setup_dma_ops(dev, attr == DEV_DMA_COHERENT);
 
 	return 0;
 }

drivers/hv/hv_common.c

@@ -561,11 +561,7 @@ EXPORT_SYMBOL_GPL(hv_query_ext_cap);
 
 void hv_setup_dma_ops(struct device *dev, bool coherent)
 {
-	/*
-	 * Hyper-V does not offer a vIOMMU in the guest
-	 * VM, so pass 0/NULL for the IOMMU settings
-	 */
-	arch_setup_dma_ops(dev, 0, 0, coherent);
+	arch_setup_dma_ops(dev, coherent);
 }
 EXPORT_SYMBOL_GPL(hv_setup_dma_ops);